Image Retrieval Based on Texture in DCT Compressed Domain

Image retrieval based on texture in DCT compressed domain is proposed by introducing the spatial information of DCT blocks and DCT coefficients into the feature extraction. Firstly, the definition of complex is introduced and then texture information is described by a complex histogram. Then, based on the analysis of the effect of the DCT coefficients on the retrieval precision, the weighted function for the histogram is presented. The statistical distribution of DCT blocks and the spatial distribution of DCT coefficients are taken into account in this paper, thus avoiding the mistaken retrieval and losing retrieval. The experiment results show that the new method has a good performance both in retrieval efficiency and effectiveness.